KEYNOTE: Trust in Optimization Algorithms – The End User Perspective

Tobias Rodemann, Honda Research Institute Europe, GERMANY. ABSTRACT: Evolutionary Algorithms have a potentially wide-spread usage. They can deal with various types of design parameters, constraints and objectives; non-linear, discontinuous, noisy fitness landscapes and many, even conflicting objectives can be handled. There are numerous open-source software packages for quickly applying EA methods on various problems. In practice, however, EAs are not used as frequently as we would hope. In this talk I would like to provide some insights from industrial projects and focus especially on the perspective of the end user. I will argue that hot topics in ML like trust, transparency and explainability, also need to be considered in Computational Intelligence.